Now with the few missing people after dinner @WayHomeLi @davmoltisanti &recurring faces/ @_alexstergiou @chiaraplizzari @Sid__Bansal @JacobChalkie @prajwal_gatti @ahmad_darkhalil

Just arriving into Copenhagen on our way to Malmo for @eccvconf #ECCV2026 with current and some ex faces @bristolcs #MaVi

Our #ECCV2026 @eccvconf paper Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition now on ArXiv w/ code&data&models prajwalgatti.github.io/gen2b… Can we fill imbalanced action recognition datasets with generative images to outperform long-tail SOTA? Yes we can 🧵

We are also thrilled to host an outstanding lineup of invited speakers, including: Angela Dai @angelaqdai , Dima Damen @dimadamen , Kosta Derpanis @CSProfKGD , Andreas Geiger, Aniruddha Kembhavi @anikembhavi , Pascal Mettes @PascalMettes , and Mike Shou @MikeShou1 .

Fun fact: the apartment we rented in Oxford Summertown from 2021-2023 has accommodated @elliottszwu (CVPR20 best paper awardee) and @jianyuan_wang (CVPR25 best paper awardee) as subletters. Now also @ChuhanZhang5 - new CVPR26 best paper awardee. Grateful to be at @Oxford_VGG !!

Xiaoye will present Our #CVPR2026 work on 3D-Aware MTL! Come find Xiaoye at the poster about 3D-aware scene understanding / MTL! 📍Jun 5 Main Poster S1 / #537 📍Jun 3 PM OpenSUN3D Workshop #CV #3DV #AI

I’m looking for a PhD student with UK home fee status to join my lab at Cambridge starting this October. If you’re interested and have research experience in multimodal spatial modeling or vision-based robot learning, email me your CV. Funding deadline is approaching very soon.

Thanks Bristol Centre for Supercomputing (BriCS) for featuring our work as users of the fantastic #IsambardAI Short video featuring our research with @mwray0 @JacobChalkie @Sid__Bansal @sinha_saptarshi @terry_jhzhao00 @prajwal_gatti @bristolcs @BristolUni piped.video/watch?v=jxrnbyvB…

Special thanks @_atewari @Cambridge_Eng for visiting us @BristolUni @bristolcs for a great #MaVi Seminar on "Physical Inductive Biases for World Models" and your thoughtful 1-1s with the researchers. Have a good trip back to Cambridge and please visit us again soon,

📢 Preprint Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach arxiv.org/abs/2512.16456 masashi-hatano.github.io/pri… First work to synthesise the natural behavior of full-body priming (i.e. gazing towards) an object b4 reaching - curated from 5 public datasets. 1/3

Preprint 📢 The N-Body Problem: Parallel Execution from Single-Person Egocentric Video Input: Single-person egocentric video 👤 Out: imagine how these tasks can be performed faster by N > 1 people, correctly 👥 📎arxiv.org/abs/2512.11393 👀zhifanzhu.github.io/ego-nbod… 1/4

Don’t miss this visiting PhD opportunity in Machine Learning & Computer Vision #mavi in 2026!

Happy to have been one of the examiners for Jacob’s PhD viva. Huge congratulations to @JacobChalkie for passing with no corrections! 🎉 Amazing work on multimodal egocentric video understanding!

Super-exciting talk by @anikembhavi @wayve_ai at @BristolUni #MaVi Seminar @bristolcs today! World models for evaluating autonomous driving, GAIA evolution w GAIA3 released! End-to-end driving model &loads of insights! Thanks for visiting &spending the day talking to researchers

Excited to be at #NeurIPS 2025 San Diego in person from 1st - 8th Dec! DM me for meeting/coffee chat about #image_editing, #video_understanding, #WorldModels and #RL for common research interests, potential collaboration, startup ideas ... See you in San Diego⛴️! ! Also welcome tour, city walk, common game interests ......

If you are looking for a PhD position, Elliott’s group is an excellent choice. He offers not just cutting-edge research directions and impactful tasks but also detailed plans, constructive feedback, and personalized mentorship. These are all you need to grow as a researcher

📢 New Paper PointSt3R: Point Tracking through 3D Grounded Correspondence Can point tracking be re-formulated as pairwise frame correspondence solely? We fine-tuning MASt3R with dynamic correspondences and a visibility loss and achieve competitive point tracking results 1/3